Algoritma Genetika Untuk Optimasi Fuzzy Time Series Dalam Memprediksi Debit Air (Studi Kasus: PDAM Indramayu)

Mohamad Alfi Fauzan (Fakultas Ilmu Komputer, Universitas Brawijaya)
Budi Darma Setiawan (Fakultas Ilmu Komputer, Universitas Brawijaya)
Indriati Indriati (Fakultas Ilmu Komputer, Universitas Brawijaya)

Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Vol 3 No 1 (2019): Januari 2019

The availability of water in the country of Indonesia reaches 694 billion m3 per year, where the amount is a potential that can be utilized but only about 23% is utilized. With the increasing number of people needing clean water but low water debit distribution, the concept of forecasting or prediction is needed as one of the inputs in making decisions to increase the flow of water to be distributed. To solve these problems in this study fuzzy time series methods are optimized with genetic algorithms in predicting the distribution of water discharge. Genetic algorithm is used to optimize sub intervals in fuzzy time series. Based on the results of the test, the accuracy of the prediction results obtained using the Average Forecasting Error Rate (AFER) method obtained the percentage error rate of 15.33% which included in the good qualifications.